A practical input-to-state stability certificate for Koopman learning control is derived, separating prediction residuals from selected-channel margins and projection residuals.
and Brunton, Steven L
8 Pith papers cite this work, alongside 1,073 external citations. Polarity classification is still indexing.
8
Pith papers citing it
1,073
external citations · OpenAlex
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 8representative citing papers
The reachable subspace dynamics of LTI systems remain uniquely identifiable from any experiment, even when the full system is not.
The paper introduces diagnostic certificates that separately assess state-space coverage, lifted-feature nondegeneracy, and regression-spectrum quality for Koopman and EDMDc identification, with theoretical guarantees on the smallest singular value under a population spectral gap.
Koopman autoencoders with forcings and temporal unrolling deliver accurate year-long predictions for coastal-ocean models at 300-1400x speedup, outperforming POD in two of three cases.
Under Hankel-DMDc, lithium-ion SOC emerges as the marginally stable Koopman mode nearest the unit circle and yields a usable SOC-sensitive observable after min-max scaling.
An equation-free Koopman-surrogate method closes open trajectories into cyclic animations via Fourier-parameterized control forces cast as a linearly constrained quadratic program.
Koopman autoencoders with attention-free latent memory and online change-point re-encoding reduce long-horizon error on Duffing, Repressilator, and IRMA benchmarks while keeping low latency.
WSINDYc-MPC identifies governing dynamics more robustly than benchmarks under high noise, enabling longer prediction horizons and lower tracking errors in fusion, drone, chaos, and aircraft control tasks.
citing papers explorer
-
Input-to-State Stability Certification via Projection Residuals for Koopman Learning Control of Nonlinear Repetitive Systems
A practical input-to-state stability certificate for Koopman learning control is derived, separating prediction residuals from selected-channel margins and projection residuals.
-
Limits of Learning Linear Dynamics from Experiments
The reachable subspace dynamics of LTI systems remain uniquely identifiable from any experiment, even when the full system is not.
-
Diagnostic Certificates of Data Quality and Regression Identifiability for Koopman Identification
The paper introduces diagnostic certificates that separately assess state-space coverage, lifted-feature nondegeneracy, and regression-spectrum quality for Koopman and EDMDc identification, with theoretical guarantees on the smallest singular value under a population spectral gap.
-
Reduced-Order Surrogates for Forced Flexible Mesh Coastal-Ocean Models
Koopman autoencoders with forcings and temporal unrolling deliver accurate year-long predictions for coastal-ocean models at 300-1400x speedup, outperforming POD in two of three cases.
-
Koopman Spectral Analysis of Lithium-Ion Battery Dynamics: State of Charge as a Marginally Stable Observable
Under Hankel-DMDc, lithium-ion SOC emerges as the marginally stable Koopman mode nearest the unit circle and yields a usable SOC-sensitive observable after min-max scaling.
-
Closing Trajectories: Equation-Free Cyclic Animation via Koopman Surrogates
An equation-free Koopman-surrogate method closes open trajectories into cyclic animations via Fourier-parameterized control forces cast as a linearly constrained quadratic program.
-
Learning the Koopman Operator using Attention Free Transformers
Koopman autoencoders with attention-free latent memory and online change-point re-encoding reduce long-horizon error on Duffing, Repressilator, and IRMA benchmarks while keeping low latency.
-
WSINDy for Model Predictive Control with Applications to Fusion, Drones, and Chaos
WSINDYc-MPC identifies governing dynamics more robustly than benchmarks under high noise, enabling longer prediction horizons and lower tracking errors in fusion, drone, chaos, and aircraft control tasks.